128 citations · 387 across the 30 of their papers we have counts for
30 papers
The Snowflake Hypothesis: Training Deep GNN with One Node One Receptive field
Kun Wang, Guohao Li, Shilong Wang +6
Despite Graph Neural Networks demonstrating considerable promise in graph representation learning tasks, GNNs predominantly face significant issues with over-fitting and over-smoot…
Rail Detection: An Efficient Row-based Network and A New Benchmark
Xinpeng Li, Xiaojiang Peng
Rail detection, essential for railroad anomaly detection, aims to identify the railroad region in video frames. Although various studies on rail detection exist, neither an open be…
IncepFormer: Efficient Inception Transformer with Pyramid Pooling for Semantic Segmentation
Lihua Fu, Haoyue Tian, Xiangping Bryce Zhai +2
Semantic segmentation usually benefits from global contexts, fine localisation information, multi-scale features, etc. To advance Transformer-based segmenters with these aspects, w…
AU-Aware Vision Transformers for Biased Facial Expression Recognition
Shuyi Mao, Xinpeng Li, Qingyang Wu +1
Studies have proven that domain bias and label bias exist in different Facial Expression Recognition (FER) datasets, making it hard to improve the performance of a specific dataset…
AU-Supervised Convolutional Vision Transformers for Synthetic Facial Expression Recognition
Shuyi Mao, Xinpeng Li, Junyao Chen +1
The paper describes our proposed methodology for the six basic expression classification track of Affective Behavior Analysis in-the-wild (ABAW) Competition 2022. In Learing from S…
Video-based Smoky Vehicle Detection with A Coarse-to-Fine Framework
Xiaojiang Peng, Xiaomao Fan, Qingyang Wu +2
Automatic smoky vehicle detection in videos is a superior solution to the traditional expensive remote sensing one with ultraviolet-infrared light devices for environmental protect…
Video Frame Interpolation Based on Deformable Kernel Region
Haoyue Tian, Pan Gao, Xiaojiang Peng
Video frame interpolation task has recently become more and more prevalent in the computer vision field. At present, a number of researches based on deep learning have achieved gre…
Stereo Matching with Cost Volume based Sparse Disparity Propagation
Wei Xue, Xiaojiang Peng
Stereo matching is crucial for binocular stereo vision. Existing methods mainly focus on simple disparity map fusion to improve stereo matching, which require multiple dense or spa…
Self-Ensemling for 3D Point Cloud Domain Adaption
Qing Li, Xiaojiang Peng, Chuan Yan +2
Recently 3D point cloud learning has been a hot topic in computer vision and autonomous driving. Due to the fact that it is difficult to manually annotate a qualitative large-scale…
Spatial and Temporal Networks for Facial Expression Recognition in the Wild Videos
Shuyi Mao, Xinqi Fan, Xiaojiang Peng
The paper describes our proposed methodology for the seven basic expression classification track of Affective Behavior Analysis in-the-wild (ABAW) Competition 2021. In this task, f…
An Efficient Training Approach for Very Large Scale Face Recognition
Kai Wang, Shuo Wang, Panpan Zhang +7
Face recognition has achieved significant progress in deep learning era due to the ultra-large-scale and welllabeled datasets. However, training on the outsize datasets is time-con…
Affordance Transfer Learning for Human-Object Interaction Detection
Zhi Hou, Baosheng Yu, Yu Qiao +2
Reasoning the human-object interactions (HOI) is essential for deeper scene understanding, while object affordances (or functionalities) are of great importance for human to discov…
Detecting Human-Object Interaction via Fabricated Compositional Learning
Zhi Hou, Baosheng Yu, Yu Qiao +2
Human-Object Interaction (HOI) detection, inferring the relationships between human and objects from images/videos, is a fundamental task for high-level scene understanding. Howeve…
Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering
Qing Li, Xiaojiang Peng, Yu Qiao +1
Although unsupervised person re-identification (Re-ID) has drawn increasing research attention recently, it remains challenging to learn discriminative features without annotations…
Exploring Emotion Features and Fusion Strategies for Audio-Video Emotion Recognition
Hengshun Zhou, Debin Meng, Yuanyuan Zhang +4
The audio-video based emotion recognition aims to classify a given video into basic emotions. In this paper, we describe our approaches in EmotiW 2019, which mainly explores emotio…
Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition
Jin Ye, Junjun He, Xiaojiang Peng +2
Recent studies often exploit Graph Convolutional Network (GCN) to model label dependencies to improve recognition accuracy for multi-label image recognition. However, constructing…
AU-Guided Unsupervised Domain Adaptive Facial Expression Recognition
Kai Wang, Yuxin Gu, Xiaojiang Peng +3
The domain diversities including inconsistent annotation and varied image collection conditions inevitably exist among different facial expression recognition (FER) datasets, which…
Suppressing Mislabeled Data via Grouping and Self-Attention
Xiaojiang Peng, Kai Wang, Zhaoyang Zeng +3
Deep networks achieve excellent results on large-scale clean data but degrade significantly when learning from noisy labels. To suppressing the impact of mislabeled data, this pape…
Visual Compositional Learning for Human-Object Interaction Detection
Zhi Hou, Xiaojiang Peng, Yu Qiao +1
Human-Object interaction (HOI) detection aims to localize and infer relationships between human and objects in an image. It is challenging because an enormous number of possible co…
TTPP: Temporal Transformer with Progressive Prediction for Efficient Action Anticipation
Wen Wang, Xiaojiang Peng, Yanzhou Su +2
Video action anticipation aims to predict future action categories from observed frames. Current state-of-the-art approaches mainly resort to recurrent neural networks to encode hi…
Suppressing Uncertainties for Large-Scale Facial Expression Recognition
Kai Wang, Xiaojiang Peng, Jianfei Yang +2
Annotating a qualitative large-scale facial expression dataset is extremely difficult due to the uncertainties caused by ambiguous facial expressions, low-quality facial images, an…
A Comprehensive Study on Temporal Modeling for Online Action Detection
Wen Wang, Xiaojiang Peng, Yu Qiao +1
Online action detection (OAD) is a practical yet challenging task, which has attracted increasing attention in recent years. A typical OAD system mainly consists of three modules:…
Learning Category Correlations for Multi-label Image Recognition with Graph Networks
Qing Li, Xiaojiang Peng, Yu Qiao +1
Multi-label image recognition is a task that predicts a set of object labels in an image. As the objects co-occur in the physical world, it is desirable to model label dependencies…
Product Image Recognition with Guidance Learning and Noisy Supervision
Qing Li, Xiaojiang Peng, Liangliang Cao +3
This paper considers recognizing products from daily photos, which is an important problem in real-world applications but also challenging due to background clutters, category dive…